Back to Models
Gemini 3.5 Flash Lite
googlegoogle/gemini-3.5-flash-lite
API guide
Chat completion
Standard OpenAI-compatible chat completion. Thinking is supported with flexible levels; thinking tokens are billed as output.
cURL
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"google/gemini-3.5-flash-lite","messages":[{"role":"user","content":"Classify this ticket: billing or technical?"}]}'Structured output
Structured outputs are supported upstream, which is the main reason to reach for this tier in extraction pipelines.
cURL
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3.5-flash-lite",
"messages": [{"role":"user","content":"Extract the invoice total and currency."}],
"response_format": {"type":"json_object"}
}'Fact ledger β every claim on this page traces here
| source | URL | retrieved | |
|---|---|---|---|
| Release date | deepmind.google β | 2026-07-28 | verified |
| Knowledge cutoff | deepmind.google β | 2026-07-28 | verified |
| Input token limit | ai.google.dev β | 2026-07-28 | verified |
| Output token limit | ai.google.dev β | 2026-07-28 | verified |
| Native modalities (upstream) | ai.google.dev β | 2026-07-28 | verified |
| Supported capabilities | ai.google.dev β | 2026-07-28 | verified |
| Not supported upstream | ai.google.dev β | 2026-07-28 | verified |
| Vendor list price (Standard tier) | ai.google.dev β | 2026-07-28 | verified |
| Output throughput | blog.google β | 2026-07-28 | to verify |
| SWE-Bench Pro | deepmind.google β | 2026-07-28 | verified |
| Terminal-Bench 2.1 | deepmind.google β | 2026-07-28 | verified |
| MLE-Bench | deepmind.google β | 2026-07-28 | verified |
| OSWorld-Verified | deepmind.google β | 2026-07-28 | verified |
| CharXiv (no tools) | deepmind.google β | 2026-07-28 | verified |
| GDM-MRCR v2 (128k) | deepmind.google β | 2026-07-28 | verified |
| GDM-MRCR v2 (1M pointwise) | deepmind.google β | 2026-07-28 | verified |
| GDPval-AA v2 | deepmind.google β | 2026-07-28 | verified |
| Gemini 3.5 Flash-Lite lands as the new budget tier | blog.google β | 2026-07-28 | verified |
| When should I use Flash-Lite instead of Gemini 3.6 Flash? | deepmind.google β | 2026-07-28 | to verify |
| Does it really have the full 1M-token context window? | deepmind.google β | 2026-07-28 | to verify |
| Is audio input charged at a premium? | ai.google.dev β | 2026-07-28 | to verify |